Bridge Health Monitoring Using a Machine-Learning Strategy

This project intends to cast the structural health monitoring (SHM) problem within a statistical pattern recognition framework. Moreover, the project proposes to use techniques borrowed from speaker recognition, as this discipline deals with problems very similar to those addressed by structural health monitoring. In particular, the project is interested in speaker verification, which is the task of verifying whether the speaker is the individual he/she claims to be by analyzing his/her speech signal. It comes natural to expect that, if speaker recognition can recognize whether it is John or Jane who says the word "mom", using the same principles, it is possible to find out whether it is the healthy or the damaged bridge that provides that acceleration time history. The aim of this research is to treat these time histories as speech data and apply the speaker identification methods for open set and text independent recognition.

Language

  • English

Project

  • Status: Active
  • Funding: $184489.00
  • Contract Numbers:

    DTRT13-G-UTC28

    CAIT-UTC-NC3

  • Sponsor Organizations:

    Parsons Transportation Group

    100 Broadwa
    New York, NY  United States  10027

    Research and Innovative Technology Administration

    University Transportation Centers Program
    1200 New Jersey Avenue
    Washington, DC  United States  20590
  • Project Managers:

    Khazem, Dyab

    Szary, Pat

  • Performing Organizations:

    Columbia University

    610 SW Mudd
    500W 120th Street
    New York, New York  United States  10027
  • Principal Investigators:

    Betti, Raimondo

  • Start Date: 20140501
  • Expected Completion Date: 0
  • Actual Completion Date: 20150430
  • Source Data: RiP Project 38052

Subject/Index Terms

Filing Info

  • Accession Number: 01543443
  • Record Type: Research project
  • Source Agency: Center for Advanced Infrastructure and Transportation
  • Contract Numbers: DTRT13-G-UTC28, CAIT-UTC-NC3
  • Files: UTC, RiP
  • Created Date: Nov 15 2014 1:00AM